© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82404
    Prev
    Next
    INDEX
    Explanations

    structural characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ũng
    0.43
    DeviceInfo
    0.43
    Fact
    0.41
    rą
    0.40
    స్తుంది
    0.37
    برى
    0.37
    妏
    0.35
    ӕ
    0.34
     Ammo
    0.34
     आएगी
    0.34
    POSITIVE LOGITS
    ྂ
    0.40
     lottery
    0.38
    けれど
    0.36
     stretches
    0.36
     litter
    0.35
     malpractice
    0.35
     opcode
    0.34
    magenta
    0.34
     Lottery
    0.34
     سات
    0.33
    Activations Density 0.000%

    No Known Activations